Alex Xiao

4 papers · 2020–2022 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10)

Venues

Interspeech (4)

Top co-authors

Christian Fuegen (4) Duc Le (3) Ozlem Kalinli (3) Michael L. Seltzer (2) Jay Mahadeokar (2) Chunyang Wu (2) Yangyang Shi (2) Yatharth Saraf (2) Abdelrahman Mohamed (2) Frank Zhang (1)

Research topics

Machine Learning (4) Deep Learning (3) Speech & Audio (3) Application Areas (3) Recognition (3) Architectures (2) Learning Types (2) Optimization & Theory (1) Techniques (1)

Keywords

automatic speech recognition (3) latency optimization (2) on-device speech recognition (2) self-supervised learning (1) weakly supervised learning (1) knowledge distillation (1) low-resource learning (1) collaborative learning (1) model scaling (1) word error rate (1) sequence-level distillation (1) dynamic encoder transducer (1) layer dropout (1) encoder layer (1) real-time factor (1) dynamic encoder (1) zero-shot learning (1) encoder transducer (1) semi-supervised learning (1) few-shot learning (1)

Papers

Scaling ASR Improves Zero and Few Shot Learning Interspeech 2022 Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency Interspeech 2021 Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios Interspeech 2021 Large Scale Weakly and Semi-Supervised Learning for Low-Resource Video ASR Interspeech 2020